Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    iss

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pbs
    -0.07
    اطعة
    -0.07
     Cunningham
    -0.07
    elcome
    -0.07
     Lover
    -0.06
     strlen
    -0.06
    Dire
    -0.06
    BUFFER
    -0.06
    股票
    -0.06
    ecta
    -0.06
    POSITIVE LOGITS
     fined
    0.06
    Exercise
    0.06
     Transactions
    0.06
    食品
    0.06
    ↵    ↵    ↵
    0.06
    umbing
    0.06
    ↵↵    ↵
    0.06
     multiprocessing
    0.06
    Ground
    0.06
     UIScreen
    0.06
    Act Density 0.029%

    No Known Activations